Upload folder using huggingface_hub
Browse files- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +283 -3
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b82ba4c676b3b5446a0c3c0895e6170fde811e7522a584fefd422d795d05e4d
|
| 3 |
size 83946192
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 168150290
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6255ec5b843f16274c3a630ceda1999d9a6ff2db1125db8a13388a7d838f220
|
| 3 |
size 168150290
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44ab34006e4ff8e3ddb1b3e0970e22b7afa1b47af9f1338b5e8a38648238a8fe
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e97643a2c9855ef59e9a06836cda3285ce9299fbc4d864a30671a903ea3632d3
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -2954,6 +2954,286 @@
|
|
| 2954 |
"learning_rate": 0.0001738967827178286,
|
| 2955 |
"loss": 0.9547,
|
| 2956 |
"step": 2100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2957 |
}
|
| 2958 |
],
|
| 2959 |
"logging_steps": 5,
|
|
@@ -2961,7 +3241,7 @@
|
|
| 2961 |
"num_input_tokens_seen": 0,
|
| 2962 |
"num_train_epochs": 1,
|
| 2963 |
"save_steps": 100,
|
| 2964 |
-
"total_flos":
|
| 2965 |
"train_batch_size": 2,
|
| 2966 |
"trial_name": null,
|
| 2967 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.34152498329497366,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2954 |
"learning_rate": 0.0001738967827178286,
|
| 2955 |
"loss": 0.9547,
|
| 2956 |
"step": 2100
|
| 2957 |
+
},
|
| 2958 |
+
{
|
| 2959 |
+
"epoch": 0.31,
|
| 2960 |
+
"grad_norm": 0.333984375,
|
| 2961 |
+
"learning_rate": 0.00017372189614169947,
|
| 2962 |
+
"loss": 0.966,
|
| 2963 |
+
"step": 2105
|
| 2964 |
+
},
|
| 2965 |
+
{
|
| 2966 |
+
"epoch": 0.31,
|
| 2967 |
+
"grad_norm": 0.349609375,
|
| 2968 |
+
"learning_rate": 0.00017354651423998733,
|
| 2969 |
+
"loss": 0.9754,
|
| 2970 |
+
"step": 2110
|
| 2971 |
+
},
|
| 2972 |
+
{
|
| 2973 |
+
"epoch": 0.31,
|
| 2974 |
+
"grad_norm": 0.341796875,
|
| 2975 |
+
"learning_rate": 0.00017337063819105496,
|
| 2976 |
+
"loss": 0.928,
|
| 2977 |
+
"step": 2115
|
| 2978 |
+
},
|
| 2979 |
+
{
|
| 2980 |
+
"epoch": 0.31,
|
| 2981 |
+
"grad_norm": 0.337890625,
|
| 2982 |
+
"learning_rate": 0.00017319426917658537,
|
| 2983 |
+
"loss": 0.9721,
|
| 2984 |
+
"step": 2120
|
| 2985 |
+
},
|
| 2986 |
+
{
|
| 2987 |
+
"epoch": 0.32,
|
| 2988 |
+
"grad_norm": 0.3515625,
|
| 2989 |
+
"learning_rate": 0.00017301740838157362,
|
| 2990 |
+
"loss": 0.9716,
|
| 2991 |
+
"step": 2125
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 0.32,
|
| 2995 |
+
"grad_norm": 0.34375,
|
| 2996 |
+
"learning_rate": 0.00017284005699431896,
|
| 2997 |
+
"loss": 0.9606,
|
| 2998 |
+
"step": 2130
|
| 2999 |
+
},
|
| 3000 |
+
{
|
| 3001 |
+
"epoch": 0.32,
|
| 3002 |
+
"grad_norm": 0.341796875,
|
| 3003 |
+
"learning_rate": 0.000172662216206417,
|
| 3004 |
+
"loss": 0.9619,
|
| 3005 |
+
"step": 2135
|
| 3006 |
+
},
|
| 3007 |
+
{
|
| 3008 |
+
"epoch": 0.32,
|
| 3009 |
+
"grad_norm": 0.3359375,
|
| 3010 |
+
"learning_rate": 0.00017248388721275129,
|
| 3011 |
+
"loss": 0.9236,
|
| 3012 |
+
"step": 2140
|
| 3013 |
+
},
|
| 3014 |
+
{
|
| 3015 |
+
"epoch": 0.32,
|
| 3016 |
+
"grad_norm": 0.333984375,
|
| 3017 |
+
"learning_rate": 0.00017230507121148575,
|
| 3018 |
+
"loss": 0.9592,
|
| 3019 |
+
"step": 2145
|
| 3020 |
+
},
|
| 3021 |
+
{
|
| 3022 |
+
"epoch": 0.32,
|
| 3023 |
+
"grad_norm": 0.3359375,
|
| 3024 |
+
"learning_rate": 0.00017212576940405647,
|
| 3025 |
+
"loss": 0.9507,
|
| 3026 |
+
"step": 2150
|
| 3027 |
+
},
|
| 3028 |
+
{
|
| 3029 |
+
"epoch": 0.32,
|
| 3030 |
+
"grad_norm": 0.369140625,
|
| 3031 |
+
"learning_rate": 0.00017194598299516338,
|
| 3032 |
+
"loss": 0.9622,
|
| 3033 |
+
"step": 2155
|
| 3034 |
+
},
|
| 3035 |
+
{
|
| 3036 |
+
"epoch": 0.32,
|
| 3037 |
+
"grad_norm": 0.349609375,
|
| 3038 |
+
"learning_rate": 0.00017176571319276257,
|
| 3039 |
+
"loss": 0.9527,
|
| 3040 |
+
"step": 2160
|
| 3041 |
+
},
|
| 3042 |
+
{
|
| 3043 |
+
"epoch": 0.32,
|
| 3044 |
+
"grad_norm": 0.330078125,
|
| 3045 |
+
"learning_rate": 0.00017158496120805788,
|
| 3046 |
+
"loss": 0.9426,
|
| 3047 |
+
"step": 2165
|
| 3048 |
+
},
|
| 3049 |
+
{
|
| 3050 |
+
"epoch": 0.32,
|
| 3051 |
+
"grad_norm": 0.349609375,
|
| 3052 |
+
"learning_rate": 0.00017140372825549284,
|
| 3053 |
+
"loss": 0.9517,
|
| 3054 |
+
"step": 2170
|
| 3055 |
+
},
|
| 3056 |
+
{
|
| 3057 |
+
"epoch": 0.32,
|
| 3058 |
+
"grad_norm": 0.33984375,
|
| 3059 |
+
"learning_rate": 0.00017122201555274261,
|
| 3060 |
+
"loss": 0.9285,
|
| 3061 |
+
"step": 2175
|
| 3062 |
+
},
|
| 3063 |
+
{
|
| 3064 |
+
"epoch": 0.32,
|
| 3065 |
+
"grad_norm": 0.33984375,
|
| 3066 |
+
"learning_rate": 0.00017103982432070563,
|
| 3067 |
+
"loss": 0.9671,
|
| 3068 |
+
"step": 2180
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 0.32,
|
| 3072 |
+
"grad_norm": 0.34375,
|
| 3073 |
+
"learning_rate": 0.00017085715578349557,
|
| 3074 |
+
"loss": 0.9375,
|
| 3075 |
+
"step": 2185
|
| 3076 |
+
},
|
| 3077 |
+
{
|
| 3078 |
+
"epoch": 0.33,
|
| 3079 |
+
"grad_norm": 0.333984375,
|
| 3080 |
+
"learning_rate": 0.00017067401116843296,
|
| 3081 |
+
"loss": 0.954,
|
| 3082 |
+
"step": 2190
|
| 3083 |
+
},
|
| 3084 |
+
{
|
| 3085 |
+
"epoch": 0.33,
|
| 3086 |
+
"grad_norm": 0.345703125,
|
| 3087 |
+
"learning_rate": 0.0001704903917060371,
|
| 3088 |
+
"loss": 0.9486,
|
| 3089 |
+
"step": 2195
|
| 3090 |
+
},
|
| 3091 |
+
{
|
| 3092 |
+
"epoch": 0.33,
|
| 3093 |
+
"grad_norm": 0.337890625,
|
| 3094 |
+
"learning_rate": 0.00017030629863001764,
|
| 3095 |
+
"loss": 0.9823,
|
| 3096 |
+
"step": 2200
|
| 3097 |
+
},
|
| 3098 |
+
{
|
| 3099 |
+
"epoch": 0.33,
|
| 3100 |
+
"grad_norm": 0.330078125,
|
| 3101 |
+
"learning_rate": 0.0001701217331772664,
|
| 3102 |
+
"loss": 0.9401,
|
| 3103 |
+
"step": 2205
|
| 3104 |
+
},
|
| 3105 |
+
{
|
| 3106 |
+
"epoch": 0.33,
|
| 3107 |
+
"grad_norm": 0.34375,
|
| 3108 |
+
"learning_rate": 0.00016993669658784904,
|
| 3109 |
+
"loss": 0.9571,
|
| 3110 |
+
"step": 2210
|
| 3111 |
+
},
|
| 3112 |
+
{
|
| 3113 |
+
"epoch": 0.33,
|
| 3114 |
+
"grad_norm": 0.328125,
|
| 3115 |
+
"learning_rate": 0.0001697511901049967,
|
| 3116 |
+
"loss": 0.9801,
|
| 3117 |
+
"step": 2215
|
| 3118 |
+
},
|
| 3119 |
+
{
|
| 3120 |
+
"epoch": 0.33,
|
| 3121 |
+
"grad_norm": 0.3359375,
|
| 3122 |
+
"learning_rate": 0.00016956521497509764,
|
| 3123 |
+
"loss": 0.943,
|
| 3124 |
+
"step": 2220
|
| 3125 |
+
},
|
| 3126 |
+
{
|
| 3127 |
+
"epoch": 0.33,
|
| 3128 |
+
"grad_norm": 0.34375,
|
| 3129 |
+
"learning_rate": 0.0001693787724476889,
|
| 3130 |
+
"loss": 0.973,
|
| 3131 |
+
"step": 2225
|
| 3132 |
+
},
|
| 3133 |
+
{
|
| 3134 |
+
"epoch": 0.33,
|
| 3135 |
+
"grad_norm": 0.345703125,
|
| 3136 |
+
"learning_rate": 0.00016919186377544788,
|
| 3137 |
+
"loss": 0.9662,
|
| 3138 |
+
"step": 2230
|
| 3139 |
+
},
|
| 3140 |
+
{
|
| 3141 |
+
"epoch": 0.33,
|
| 3142 |
+
"grad_norm": 0.353515625,
|
| 3143 |
+
"learning_rate": 0.00016900449021418394,
|
| 3144 |
+
"loss": 0.9618,
|
| 3145 |
+
"step": 2235
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 0.33,
|
| 3149 |
+
"grad_norm": 0.33984375,
|
| 3150 |
+
"learning_rate": 0.00016881665302282995,
|
| 3151 |
+
"loss": 0.9454,
|
| 3152 |
+
"step": 2240
|
| 3153 |
+
},
|
| 3154 |
+
{
|
| 3155 |
+
"epoch": 0.33,
|
| 3156 |
+
"grad_norm": 0.3359375,
|
| 3157 |
+
"learning_rate": 0.00016862835346343385,
|
| 3158 |
+
"loss": 0.9414,
|
| 3159 |
+
"step": 2245
|
| 3160 |
+
},
|
| 3161 |
+
{
|
| 3162 |
+
"epoch": 0.33,
|
| 3163 |
+
"grad_norm": 0.349609375,
|
| 3164 |
+
"learning_rate": 0.00016843959280115015,
|
| 3165 |
+
"loss": 0.9437,
|
| 3166 |
+
"step": 2250
|
| 3167 |
+
},
|
| 3168 |
+
{
|
| 3169 |
+
"epoch": 0.33,
|
| 3170 |
+
"grad_norm": 0.353515625,
|
| 3171 |
+
"learning_rate": 0.00016825037230423139,
|
| 3172 |
+
"loss": 0.9761,
|
| 3173 |
+
"step": 2255
|
| 3174 |
+
},
|
| 3175 |
+
{
|
| 3176 |
+
"epoch": 0.34,
|
| 3177 |
+
"grad_norm": 0.345703125,
|
| 3178 |
+
"learning_rate": 0.00016806069324401977,
|
| 3179 |
+
"loss": 0.9458,
|
| 3180 |
+
"step": 2260
|
| 3181 |
+
},
|
| 3182 |
+
{
|
| 3183 |
+
"epoch": 0.34,
|
| 3184 |
+
"grad_norm": 0.33203125,
|
| 3185 |
+
"learning_rate": 0.00016787055689493837,
|
| 3186 |
+
"loss": 0.9676,
|
| 3187 |
+
"step": 2265
|
| 3188 |
+
},
|
| 3189 |
+
{
|
| 3190 |
+
"epoch": 0.34,
|
| 3191 |
+
"grad_norm": 0.341796875,
|
| 3192 |
+
"learning_rate": 0.00016767996453448283,
|
| 3193 |
+
"loss": 0.9729,
|
| 3194 |
+
"step": 2270
|
| 3195 |
+
},
|
| 3196 |
+
{
|
| 3197 |
+
"epoch": 0.34,
|
| 3198 |
+
"grad_norm": 0.33984375,
|
| 3199 |
+
"learning_rate": 0.00016748891744321263,
|
| 3200 |
+
"loss": 0.9613,
|
| 3201 |
+
"step": 2275
|
| 3202 |
+
},
|
| 3203 |
+
{
|
| 3204 |
+
"epoch": 0.34,
|
| 3205 |
+
"grad_norm": 0.34765625,
|
| 3206 |
+
"learning_rate": 0.0001672974169047425,
|
| 3207 |
+
"loss": 0.9453,
|
| 3208 |
+
"step": 2280
|
| 3209 |
+
},
|
| 3210 |
+
{
|
| 3211 |
+
"epoch": 0.34,
|
| 3212 |
+
"grad_norm": 0.33203125,
|
| 3213 |
+
"learning_rate": 0.00016710546420573377,
|
| 3214 |
+
"loss": 0.9538,
|
| 3215 |
+
"step": 2285
|
| 3216 |
+
},
|
| 3217 |
+
{
|
| 3218 |
+
"epoch": 0.34,
|
| 3219 |
+
"grad_norm": 0.349609375,
|
| 3220 |
+
"learning_rate": 0.00016691306063588583,
|
| 3221 |
+
"loss": 0.9484,
|
| 3222 |
+
"step": 2290
|
| 3223 |
+
},
|
| 3224 |
+
{
|
| 3225 |
+
"epoch": 0.34,
|
| 3226 |
+
"grad_norm": 0.3359375,
|
| 3227 |
+
"learning_rate": 0.0001667202074879274,
|
| 3228 |
+
"loss": 0.9501,
|
| 3229 |
+
"step": 2295
|
| 3230 |
+
},
|
| 3231 |
+
{
|
| 3232 |
+
"epoch": 0.34,
|
| 3233 |
+
"grad_norm": 0.3515625,
|
| 3234 |
+
"learning_rate": 0.00016652690605760775,
|
| 3235 |
+
"loss": 0.9739,
|
| 3236 |
+
"step": 2300
|
| 3237 |
}
|
| 3238 |
],
|
| 3239 |
"logging_steps": 5,
|
|
|
|
| 3241 |
"num_input_tokens_seen": 0,
|
| 3242 |
"num_train_epochs": 1,
|
| 3243 |
"save_steps": 100,
|
| 3244 |
+
"total_flos": 3.2343958171460567e+18,
|
| 3245 |
"train_batch_size": 2,
|
| 3246 |
"trial_name": null,
|
| 3247 |
"trial_params": null
|